{"as_of":"2026-08-16T03:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0d9809439c2c5e30d60a6c8c61ce79bb4c8f400455e3ecfa7bf941b163aa3b0c","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T14:39:15.796174Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T16:15:16.090502Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.09018","last_updated":"2025-08-24T21:17:07Z","snapshot_observed_at":"2026-08-13T05:24:44.411681Z","submitted_at":"2023-11-15T15:02:23Z","title":"On the Foundation of Distributionally Robust Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.09018","snapshot_observed_at":"2026-08-07T15:42:57.347174Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.14458","last_updated":"2025-05-20T14:55:42Z","snapshot_observed_at":"2026-08-11T23:21:49.226875Z","submitted_at":"2025-05-20T14:55:42Z","title":"Adaptive Estimation of the Transition Density of Controlled Markov Chains","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:57.347174Z"},"links":{"cited_paper":"/paper/2311.09018","citing_paper":"/paper/2505.14458"},"observation_digest":"sha256:3c63f139c77663abc1a75cc6fd084b919a3a2f8920221f54860112a4f9bbde04","observation_id":"cdf31e3a-7964-444c-bc40-77b90582c748","resolution":{"observed_at":"2026-08-07T15:42:57.347174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09018","last_updated":"2025-08-24T21:17:07Z","snapshot_observed_at":"2026-08-13T05:24:44.411681Z","submitted_at":"2023-11-15T15:02:23Z","title":"On the Foundation of Distributionally Robust Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.09018","snapshot_observed_at":"2026-08-06T20:27:17.303633Z","title":"On the foundation of distributionally robust reinforcement learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.03068","last_updated":"2025-07-18T07:38:55Z","snapshot_observed_at":"2026-08-13T20:07:34.398656Z","submitted_at":"2025-07-03T17:57:12Z","title":"Mitigating Goal Misgeneralization via Minimax Regret","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-06T20:27:17.303633Z"},"links":{"cited_paper":"/paper/2311.09018","citing_paper":"/paper/2507.03068"},"observation_digest":"sha256:cfe5ab957904c1b274510710ea8cf4493cad38babc9e709fceb92656b39bb9ef","observation_id":"3ccb9edc-595e-4760-bcf0-b88be9f14093","resolution":{"observed_at":"2026-08-06T20:27:17.303633Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09018","last_updated":"2025-08-24T21:17:07Z","snapshot_observed_at":"2026-08-13T05:24:44.411681Z","submitted_at":"2023-11-15T15:02:23Z","title":"On the Foundation of Distributionally Robust Reinforcement Learning","version":4},"cited_work":{"arxiv_id":"2311.09018","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.09018","snapshot_observed_at":"2026-08-06T16:15:16.090502Z","title":"On the Foundation of Distributionally Robust Reinforcement Learning","venue":"cs.LG","work_id":"fa5557c9-34c9-480c-b761-7205f05d0038","year":2023},"citing_paper":{"arxiv_id":"2507.14444","last_updated":"2025-07-19T02:42:41Z","snapshot_observed_at":"2026-08-14T15:14:45.544908Z","submitted_at":"2025-07-19T02:42:41Z","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","version":1},"reference_index":125,"source":"pdf_text","source_observed_at":"2026-08-06T16:15:15.920454Z"},"links":{"cited_paper":"/paper/2311.09018","citing_paper":"/paper/2507.14444"},"observation_digest":"sha256:094ef94886aea4eb5bbc20c393d567ea445fe5387e4e7622a1ee07a4bd56a3c7","observation_id":"5682792e-7a2b-417a-b869-2c21e11e54b4","resolution":{"observed_at":"2026-08-06T16:15:16.093893Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09018","last_updated":"2025-08-24T21:17:07Z","snapshot_observed_at":"2026-08-13T05:24:44.411681Z","submitted_at":"2023-11-15T15:02:23Z","title":"On the Foundation of Distributionally Robust Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.09018","snapshot_observed_at":"2026-08-15T14:39:15.796174Z","title":"arXiv preprint arXiv:2311.09018 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.06545","last_updated":"2026-08-06T19:49:48Z","snapshot_observed_at":"2026-08-15T15:50:51.948251Z","submitted_at":"2026-08-06T19:49:48Z","title":"Robust Average-Reward Markov Decision Processes: Minimax-Optimal Learning via Plug-in Reductions","version":1},"reference_index":149,"source":"arxiv_source","source_observed_at":"2026-08-15T14:39:15.796174Z"},"links":{"cited_paper":"/paper/2311.09018","citing_paper":"/paper/2608.06545"},"observation_digest":"sha256:bcfb74044a1758c9d92fa7d02e766b0e7f90e68e4230a5f3ce4fe4583ecc7293","observation_id":"4d444daa-3981-4148-90b4-eb6aa8a8c34f","resolution":{"observed_at":"2026-08-15T14:39:15.796174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2311.09018/citation-record","integrity":"/paper/2311.09018/integrity","json":"/paper/2311.09018/citation-record.json","paper":"/paper/2311.09018"},"outbound":[],"paper":{"arxiv_id":"2311.09018","last_updated":"2025-08-24T21:17:07Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T05:24:44.411681Z","submitted_at":"2023-11-15T15:02:23Z","title":"On the Foundation of Distributionally Robust Reinforcement Learning"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2311.09018."}